Embedding Ontologies via Incorporating Extensional and Intensional Knowledge
arXiv:2402.01677 · doi:10.3724/2096-7004.di.2024.0088
Abstract
Ontologies contain rich knowledge within domain, which can be divided into two categories, namely extensional knowledge and intensional knowledge. Extensional knowledge provides information about the concrete instances that belong to specific concepts in the ontology, while intensional knowledge details inherent properties, characteristics, and semantic associations among concepts. However, existing ontology embedding approaches fail to take both extensional knowledge and intensional knowledge into fine consideration simultaneously. In this paper, we propose a novel ontology embedding approach named EIKE (Extensional and Intensional Knowledge Embedding) by representing ontologies in two spaces, called extensional space and intensional space. EIKE presents a unified framework for embedding instances, concepts and their relations in an ontology, applying a geometry-based method to model extensional knowledge and a pretrained language model to model intensional knowledge, which can capture both structure information and textual information. Experimental results show that EIKE significantly outperforms state-of-the-art methods in three datasets for both triple classification and link prediction, indicating that EIKE provides a more comprehensive and representative perspective of the domain.
References in corpus (8)
- Poincaré Embeddings for Learning Hierarchical Representations
- Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations
- From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer
- KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
- Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
- Dual-Geometric Space Embedding Model for Two-View Knowledge Graphs
- Relational Message Passing for Fully Inductive Knowledge Graph Completion
- Source-Aware Embedding Training on Heterogeneous Information Networks